Connect your application to LaoZhang API

Use https://api2.laozhang.ai to call LaoZhang API. OpenAI clients use a base URL ending in /v1; Google Gen AI and Anthropic clients use the host root. Choose the format your application already uses, then select a model available to your API key’s group.

Get an API key

Create a model API key in Token management. Check its group, balance, and model permissions in Models and pricing. Set the key as an environment variable in the terminal where you will run the examples:

export LAOZHANG_API_KEY="YOUR_LAOZHANG_API_KEY"

Replace the placeholder with your key. Keep credentials on your server, out of browser bundles, source control, and public logs. Account management AccessTokens are separate credentials; use the balance query guide for account-data requests. The examples use gpt-5.4-mini for text, gemini-3.8-flash for native Gemini text, and gpt-image-2-vip for images. If your token group uses another model, copy its exact ID from the console.

Send a text request

Chat Completions accepts a messages array. Use Bearer authentication and a JSON request body:

curl --fail-with-body --max-time 120 \
  "https://api2.laozhang.ai/v1/chat/completions" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4-mini",
    "messages": [{"role": "user", "content": "Reply only with: connected"}]
  }'

The answer appears in choices[0].message.content. For this prompt, expect connected. Replace the message content with your own prompt to use the same request in your application.

OpenAI SDK

The OpenAI SDK builds the endpoint path, so set its base URL to https://api2.laozhang.ai/v1 without adding /chat/completions.

Python
Node.js

Install the SDK:

python -m pip install openai

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["LAOZHANG_API_KEY"],
    base_url="https://api2.laozhang.ai/v1",
    timeout=120.0,
    max_retries=0,
)
response = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[{"role": "user", "content": "Reply only with: connected"}],
)
print(response.choices[0].message.content)

Install the SDK with npm install openai, then save this code in an .mjs file and run it with Node.js:

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.LAOZHANG_API_KEY,
  baseURL: "https://api2.laozhang.ai/v1",
  timeout: 120_000,
  maxRetries: 0,
});
const response = await client.chat.completions.create({
  model: "gpt-5.4-mini",
  messages: [{ role: "user", content: "Reply only with: connected" }],
});
console.log(response.choices[0].message.content);

These examples disable automatic retries so your application can decide when to repeat a request. Add optional parameters according to the selected model’s documentation. Sampling controls, output limits, structured output, and tools are model-specific; see the Chat Completions reference.

Responses API

The Responses API uses input in the request and output in the response. Its request body is different from Chat Completions.

cURL
Python

curl --fail-with-body --max-time 120 \
  "https://api2.laozhang.ai/v1/responses" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4-mini",
    "input": "Reply only with: connected"
  }'

Use the same openai package installed above:

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["LAOZHANG_API_KEY"],
    base_url="https://api2.laozhang.ai/v1",
    timeout=120.0,
    max_retries=0,
)
response = client.responses.create(
    model="gpt-5.4-mini",
    input="Reply only with: connected",
)
print(response.output_text)

For raw JSON, collect the text values from content items whose type is output_text within the output array. The SDK’s output_text helper does this for you. Other output items can contain reasoning or tool calls, so the first item is not necessarily the text answer. For applications that need conversation history, retain the messages your next request requires. Server-side state, previous_response_id, and built-in tools depend on the selected model and endpoint. See the OpenAI Responses reference for upstream field definitions and the Data Policy for data handling.

Generate an image

Send a JSON prompt to the Images generation endpoint:

curl --fail-with-body --max-time 360 \
  "https://api2.laozhang.ai/v1/images/generations" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2-vip",
    "prompt": "A blue ceramic cup on a white table, soft natural light, product photography."
  }' \
  -o generation-response.json

The response is JSON. For this model, read the image bytes from data[0].b64_json. Install Pillow with python -m pip install pillow, then save the image:

python - <<'PY'
import base64
import io
import json
from pathlib import Path
from PIL import Image

response = json.loads(Path("generation-response.json").read_text())
raw = base64.b64decode(response["data"][0]["b64_json"], validate=True)
with Image.open(io.BytesIO(raw)) as image:
    image.load()
    extension = {"PNG": "png", "JPEG": "jpg", "WEBP": "webp"}[image.format]
    output = Path(f"generated.{extension}")
    output.write_bytes(raw)
    print(f"Saved {output}")
PY

Open the saved file to view the generated image. For a complete Python SDK example and model options, see Generate an image.

Edit an image

Place a reference image named input.png in your current directory. Upload it with the instructions as multipart form data:

curl --fail-with-body --max-time 360 \
  "https://api2.laozhang.ai/v1/images/edits" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -F "model=gpt-image-2-vip" \
  -F "image[]=@input.png" \
  -F 'prompt=Change the background to pale blue. Keep the subject unchanged.' \
  -o edit-response.json

The @ syntax uploads the file contents. Let cURL set the multipart content type and boundary; do not add Content-Type: application/json to this request. Install Pillow with python -m pip install pillow if needed, then save the returned image:

python - <<'PY'
import base64
import io
import json
from pathlib import Path
from PIL import Image

response = json.loads(Path("edit-response.json").read_text())
raw = base64.b64decode(response["data"][0]["b64_json"], validate=True)
with Image.open(io.BytesIO(raw)) as image:
    image.load()
    extension = {"PNG": "png", "JPEG": "jpg", "WEBP": "webp"}[image.format]
    output = Path(f"edited.{extension}")
    output.write_bytes(raw)
    print(f"Saved {output}")
PY

Compare the saved image with your reference. For the Python SDK upload and more details on results, see Edit an image. Image dimensions, quality settings, and output formats depend on the model; use the matching model guide when adding these options.

Call Gemini with its native API

Gemini’s native API uses contents[].parts[] rather than OpenAI messages:

curl --fail-with-body --max-time 120 \
  "https://api2.laozhang.ai/v1beta/models/gemini-3.8-flash:generateContent" \
  -H "Authorization: Bearer $LAOZHANG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [{"text": "Reply only with: connected"}]
    }]
  }'

Read the text parts in candidates[].content.parts[]. If no text is present, inspect finishReason and promptFeedback. For the Google Gen AI SDK, use the host root https://api2.laozhang.ai with api_version="v1beta". The SDK adds the model path and API key header. The Gemini reference includes a complete Python example, both authentication header options, and image-input instructions.

Call Claude with its native API

Applications built around Anthropic content blocks use:

POST https://api2.laozhang.ai/v1/messages

Set the Anthropic SDK base URL to https://api2.laozhang.ai. Follow the Claude integration guide for the model ID, required headers, and message format. Native Anthropic content blocks and OpenAI message objects use different request and response structures.

More API operations

Models API: discover model IDs for your application.
Embeddings: turn text into vectors.
Audio transcription: upload audio and receive a transcript.
Moderation: submit content for classification.

Resolve common errors

Status	What to check
400	JSON syntax, field types, model options, and input length.
401	The API key, authentication header, and key expiration.
403	Token group, model permissions, and account restrictions.
404	The final URL and exact model ID; look for a duplicated `/v1`.
429	The error body for rate, concurrency, capacity, or balance limits.
5xx or timeout	Network conditions, model availability, and call logs.

Correct invalid requests before retrying. For temporary failures, use bounded backoff and avoid stacking SDK retries with application retries. A client timeout does not cancel generation or establish whether a charge occurred. Check call logs before resubmitting an image request. If you need support, provide the time, model, endpoint, token group, and redacted error. Billing and refunds follow the Terms.

Use these docs in an AI coding tool

Give your coding assistant the target model, task, and one of these documentation links:

skill.md: integration instructions for coding tools.
llms.txt: an index for finding the relevant page.
llms-full.txt: the full public documentation export.

Start with the index if your tool has a limited context window. Supply credentials through the environment instead of pasting them into prompts.

Essentials

Text APIs

Video Generation APIs

Image Generation APIs

AI Understanding

Connect your application to LaoZhang API

Get an API key

Send a text request

OpenAI SDK

Responses API

Generate an image

Edit an image

Call Gemini with its native API

Call Claude with its native API

More API operations

Resolve common errors

Use these docs in an AI coding tool

API references

​Get an API key

​Send a text request

​OpenAI SDK

​Responses API

​Generate an image

​Edit an image

​Call Gemini with its native API

​Call Claude with its native API

​More API operations

​Resolve common errors

​Use these docs in an AI coding tool

​API references

Get an API key

Send a text request

OpenAI SDK

Responses API

Generate an image

Edit an image

Call Gemini with its native API

Call Claude with its native API

More API operations

Resolve common errors

Use these docs in an AI coding tool

API references